LG AI Research· EXAONE

[AI Ethics Seminar 2025 EP.3] Agentic AI Threat Modeling and Guardrail Implementation Strategy

LG AI Research's AI Ethics Seminar discusses threat modeling for Agentic AI, highlighting new security challenges such as indirect prompt injection and intent breaking, and emphasizing the shift from content safety to action safety and goal integrity.

From the source

Indirect prompt injection (IPI) occurs when an attacker embeds a malicious prompt within external data sources – such as webpages or emails – that the agent can access, enabling remote control over the agent.

lgresearch.ai

Announced

24 Dec 2025 00:00 UTC

Detected

28 Aug 2026 22:20 UTC (+247d after)